jellyrock/jellyrock / .claude/skills/focus
focus
VerifiedSession-start orchestrator for JellyRock. Reads the same `scripts/catchup-state.js` state `/catchup` uses, ranks what is actionable by a fixed order, recommends the single best next move (the rule that picked it, the state behind it, 1-3 alternatives), and hands it off by printing the one command to type: `/resume-project <slug>` for a tracked project, `/start-project` for project-shaped new work, a skill that covers the pick (`/ci-triage`, `/issue-triage`, `/runtime-triage`, `/server-upgrade` for investigations; `/new-setting`, `/new-migration`, `/new-api-version`, `/translation-add` for recurring "add an X" work; `/done` or `/log` for a journal fix), or, for an ad-hoc one-off, a researched, fork-free plan (forks asked in chat, saved to `.claude/plans/`) run by a Sonnet sub-agent that `/focus` supervises and reviews. Recommend-then-confirm, one command per route. Use at the start of a session when you want the next move picked rather than a state dump; `--area=<name>` scopes it to a subsystem. Distinct from `/catchup` (state briefing, never picks) and `/ramp` (area deep-dive briefing).
Security report
VerifiedStatic analysis of one exact version. It reduces risk and shows evidence; it does not certify that a skill is safe.
- Commit
87f19f0039a66c9345de85e4547f7d3e4ed94088- Content hash
82e514e12b90d9660d22103af0af7794dc575f7b99e494ea992621c4332772ef- Scanned
- 2026-11-17
- Scanner version
- skillxone-scan-1.0.0
- Policy version
- 0.1-draft
- Decision
- Every required check completed with no open blocking or medium findings.
- Verification expires
- 2026-12-17
Findings (1 info)
The skill ships an executable script. Review it before allowing an agent to run it.
#!/usr/bin/env bashSuggested fix: None required. Informational.
Checks run
- prompt-injection
- dangerous-commands
- credentials
- network
- file-access
- integrity
Checks skipped
- dependencies: No dependency manifest in the skill directory.
- gitleaks: gitleaks is not installed on this host.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |